Interpolative Distillation for Unifying Biased and Debiased Recommendation

Abstract

Most recommender systems evaluate model performance offline through either: 1) normal biased test on factual interactions; or 2) debiased test with records from the randomized controlled trial. In fact, both tests only reflect part of the whole picture: factual interactions are collected from the recommendation policy, fitting them better implies benefiting the platform with higher click or conversion rate; in contrast, debiased test eliminates system-induced biases and thus is more reflective of user true preference. Nevertheless, we find that existing models exhibit trade-off on the two tests, and there lacks methods that perform well on both tests.

Topics & Concepts